Input-level Inductive Biases for 3D Reconstruction
Much of the recent progress in 3D vision has been driven by the development of specialized architectures that incorporate geometrical inductive biases. In this paper we tackle 3D reconstruction using a domain agnostic architecture and study how instead to inject the same type of inductive biases directly as extra inputs to the model. This approach makes it possible to apply existing general models, such as Perceivers, on this rich domain, without the need for architectural changes, while simultaneously maintaining data efficiency of bespoke models. In particular we study how to encode cameras, projective ray incidence and epipolar geometry as model inputs, and demonstrate competitive multi-view depth estimation performance on multiple benchmarks.
Code (0)
등록된 구현이 없습니다.
Tasks
3D ReconstructionDepth EstimationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
RING-NeRF : Rethinking Inductive Biases for Versatile and Efficient Neural Fields
Recent advances in Neural Fields mostly rely on developing task-specific supervision which often complicates the models. Rather than developing hard-to-combine and specific modules, another approach generally overlooked …
3D ReconstructionNeRFOn the generalization of learning-based 3D reconstruction
State-of-the-art learning-based monocular 3D reconstruction methods learn priors over object categories on the training set, and as a result struggle to achieve reasonable generalization to object categories unseen durin…
3D ReconstructionPositionReconstruction Bottlenecks in Object-Centric Generative Models
A range of methods with suitable inductive biases exist to learn interpretable object-centric representations of images without supervision. However, these are largely restricted to visually simple images; robust object …
ObjectObject DiscoverySyntactic Inductive Biases for Deep Learning Methods
In this thesis, we try to build a connection between the two schools by introducing syntactic inductive biases for deep learning models. We propose two families of inductive biases, one for constituency structure and ano…
Deep LearningInductive BiasRelational inductive biases on attention mechanisms
Inductive learning aims to construct general models from specific examples, guided by biases that influence hypothesis selection and determine generalization capacity. In this work, we focus on characterizing the relatio…